Cover Image

Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Major, Noam, Razmadze, Kathy, Shavit, Yoli
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
by: Aviv, Gilad, et al.
Published: (2025)

KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision
by: Yanko, Maya, et al.
Published: (2026)

DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training
by: Wu, Yuemin, et al.
Published: (2025)

Towards Self-Supervised Foundation Models for Critical Care Time Series
by: Jagd, Katja Naasunnguaq, et al.
Published: (2025)

Measuring Pre-training Data Quality without Labels for Time Series Foundation Models
by: Wen, Songkang, et al.
Published: (2024)

EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models
by: Zhou, Xinxing, et al.
Published: (2026)

Self-Supervised Radio Pre-training: Toward Foundational Models for Spectrogram Learning
by: Aboulfotouh, Ahmed, et al.
Published: (2024)

Quantifying Representation Reliability in Self-Supervised Learning Models
by: Park, Young-Jin, et al.
Published: (2023)

Self-Supervised Learning for Time Series: Contrastive or Generative?
by: Liu, Ziyu, et al.
Published: (2024)

QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models
by: Wang, Hao, et al.
Published: (2025)

Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series
by: Chang, Ching, et al.
Published: (2024)

OSF: On Pre-training and Scaling of Sleep Foundation Models
by: Shuai, Zitao, et al.
Published: (2026)

Self-Supervised Learning for Time Series: A Review & Critique of FITS
by: Eefsen, Andreas Løvendahl, et al.
Published: (2024)

Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
by: Santamaria-Valenzuela, Inmaculada, et al.
Published: (2025)

Synthetic Series-Symbol Data Generation for Time Series Foundation Models
by: Wang, Wenxuan, et al.
Published: (2025)

TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification
by: Yeh, Chin-Chia Michael, et al.
Published: (2025)

Membership Inference Attacks Against Time-Series Models
by: Koren, Noam, et al.
Published: (2024)

Transfer Learning with Pre-trained Conditional Generative Models
by: Yamaguchi, Shin'ya, et al.
Published: (2022)

PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse
by: Vaaras, Einari, et al.
Published: (2024)

Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection
by: Chen, Yutong, et al.
Published: (2024)

Leveraging Generic Time Series Foundation Models for EEG Classification
by: Gnassounou, Théo, et al.
Published: (2025)

LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
by: Xu, Yuanjian, et al.
Published: (2024)

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare
by: Song, Ziyang, et al.
Published: (2023)

Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning
by: Song, Ziyang, et al.
Published: (2024)

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
by: Cao, Defu, et al.
Published: (2024)

Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning
by: Mattos, João, et al.
Published: (2026)

UniMTS: Unified Pre-training for Motion Time Series
by: Zhang, Xiyuan, et al.
Published: (2024)

Generative Modeling of Clinical Time Series via Latent Stochastic Differential Equations
by: Aslanimoghanloo, Muhammad, et al.
Published: (2025)

UTICA: Multi-Objective Self-Distllation Foundation Model Pretraining for Time Series Classification
by: Moakher, Yessin, et al.
Published: (2026)

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
by: Ekambaram, Vijay, et al.
Published: (2024)

Estimating Time Series Foundation Model Transferability via In-Context Learning
by: Yao, Qingren, et al.
Published: (2025)

Foundation Models for Time Series: A Survey
by: Kottapalli, Siva Rama Krishna, et al.
Published: (2025)

Transformers and Their Roles as Time Series Foundation Models
by: Wu, Dennis, et al.
Published: (2025)

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
by: Moroshan, Vladyslav, et al.
Published: (2025)

TripCast: Pre-training of Masked 2D Transformers for Trip Time Series Forecasting
by: Liao, Yuhua, et al.
Published: (2024)

Time Series Foundation Models for Process Model Forecasting
by: Yu, Yongbo, et al.
Published: (2025)

Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
by: Wang, Wenxuan, et al.
Published: (2025)

This Time is Different: An Observability Perspective on Time Series Foundation Models
by: Cohen, Ben, et al.
Published: (2025)

A Survey on Time-Series Pre-Trained Models
by: Ma, Qianli, et al.
Published: (2023)

Foundation Model for Cardiac Time Series via Masked Latent Attention
by: Vandenhirtz, Moritz, et al.
Published: (2026)